Qwen3-thirukkural-tamil-v2

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Qwen3-thirukkural-tamil-v2

This model is a fine-tuned version of Qwen/Qwen3-0.6B on an Thirukkural dataset. It achieves the following results on the evaluation set:

• Loss: 0.2986

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "tidelganesh/Qwen3-thirukkural-tamil"  # your repo
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, dtype="auto")

messages = [{"role": "user", "content": "பொறையுடைமை அதிகாரத்தில் வரும் 158ஆம் குறளைத் தருக."}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

output = model.generate(
    **inputs, max_new_tokens=150,
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Framework versions

• Transformers 5.14.1
• Pytorch 2.8.0+cu128
• Datasets 5.0.0
• Tokenizers 0.22.2